Skip to main content
Glama

Procesio MCP Server

This is a Model Context Protocol (MCP) server designed to interact with the Procesio automation platform API. It allows language models and other MCP clients to list, view, and manage Procesio workflows and instances.

This server uses API Key/Value authentication.

Features

Tools

The server currently provides the following tools:

  • procesio_test_authentication:

    • Description: Tests the API Key/Value authentication by fetching current user details.

    • Input: None

    • Output: JSON object with user details on success.

  • procesio_list_projects:

    • Description: Lists available Procesio process templates (workflows).

    • Input (Optional): pageNumber (integer, default: 1), pageItemCount (integer, default: 20)

    • Output: JSON object containing a paginated list of process templates.

  • procesio_get_project_details:

    • Description: Gets details for a specific Procesio process template (workflow).

    • Input (Required): projectId (string - UUID of the process template)

    • Output: JSON object with the detailed configuration of the specified process template.

  • procesio_launch_project:

    • Description: Launches an instance of a specific Procesio process template (workflow).

    • Input (Required): projectId (string - UUID of the process template)

    • Input (Optional): payload (object), runSynchronous (boolean), debugMode (boolean), secondsTimeOut (integer), connectionId (string - passed as header)

    • Output: JSON object with details about the launched instance (e.g., instance ID). Note: Launch may fail if the project is invalid.

  • procesio_get_instance_status:

    • Description: Gets the status of a running or completed process instance.

    • Input (Required): instanceId (string - UUID of the process instance)

    • Input (Optional): flowTemplateId (string - UUID of the original template), isArchived (boolean)

    • Output: JSON object with the status details of the specified instance.

Related MCP server: PacedLoop MCP Server

Configuration

This server requires environment variables to be set for authentication and API endpoint configuration. These can be provided via:

  1. .env file: Create a .env file in the project root (procesio-mcp-server/.env) with the following content:

    PROCESIO_API_KEY='YOUR_API_KEY'
    PROCESIO_API_VALUE='YOUR_API_VALUE'
    PROCESIO_USERNAME='your_procesio_username' # Still needed for initial check, though not used for auth
    PROCESIO_PASSWORD='your_procesio_password' # Still needed for initial check, though not used for auth
    PROCESIO_WEB_API_URL='https://webapi.procesio.app/' # Or your specific instance URL
    PROCESIO_REALM='procesio01' # Or your specific realm if different
  2. MCP Settings File: Alternatively, configure these directly in the env block of your MCP client's settings file (e.g., cline_mcp_settings.json or claude_desktop_config.json). This method is preferred when running via an MCP client as it ensures the variables are correctly passed to the server process.

    {
      "mcpServers": {
        "procesio": {
          "command": "node",
          "args": [
            "/path/to/procesio-mcp-server/build/index.js"
          ],
          "env": {
            "PROCESIO_API_KEY": "YOUR_API_KEY",
            "PROCESIO_API_VALUE": "YOUR_API_VALUE",
            "PROCESIO_USERNAME": "your_procesio_username",
            "PROCESIO_PASSWORD": "your_procesio_password",
            "PROCESIO_WEB_API_URL": "https://webapi.procesio.app/",
            "PROCESIO_REALM": "procesio01"
          },
          "disabled": false,
          "autoApprove": []
        }
      }
    }

    Replace /path/to/ with the actual path to the server directory.

Development

Requires Node.js (LTS version recommended, see .nvmrc).

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Running Locally (for testing)

Ensure environment variables are set (e.g., via .env or exported in your shell).

npm run build
node build/index.js

The server will listen on stdio for MCP requests.

Certified by MCP Review

License

This project is licensed under the Apache License, Version 2.0. See the LICENSE file for details.

Available Tools

1 tool
create_noteB

Create a new note

Inputs: title (required), content (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'create_note' has a clearly distinct purpose, and an agent cannot misselect between non-existent alternatives.

    Naming Consistency5/5

    The naming pattern is trivially consistent as there is only one tool. The tool name 'create_note' follows a clear verb_noun pattern, and with no other tools to compare, there are no deviations or inconsistencies.

    Tool Count2/5

    A single tool is too few for a server named 'Procesio MCP Server', which suggests a broader scope. While 'create_note' is a specific function, the server name implies more comprehensive process or note management capabilities, making the tool count feel incomplete and under-scoped.

    Completeness2/5

    The server is severely incomplete for note management. With only a 'create_note' tool, there are significant gaps: no ability to read, update, delete, list, or search notes. This will cause agent failures as basic workflows (e.g., retrieving or modifying existing notes) are impossible.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables interaction with the hosted PacedLoop API to manage workflows and monitor process runs. It provides tools for workflow CRUD operations, run execution management, and access to detailed performance analytics within MCP-capable clients.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI models to manage workflows, credentials, nodes, templates, and monitor executions on the n8n automation platform through a standardized MCP interface.
      52,905 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to programmatically create, manage, and orchestrate n8n workflows through a standardized MCP interface.
      MIT